Data

Model

Normalization

None

Z-standard

Min-Max

MaxAbs (−1, 1)

Quantile Transform

Quantile Normalize

Bivariate Normal - Binary Target

Logistic

Total Risk

0.290

0.462

0.474

0.485

0.482

0.290

Bias

0.290

0.220

0.228

0.237

0.234

0.290

Variance

0.000

0.242

0.246

0.438

0.248

0.000

Noise

0.000

0.000

0.000

0.190

0.000

0.000

Variance-Bias Ratio

0.000

1.098

1.080

1.850

1.061

0.000

Percent Change from Raw

~

159.319

163.488

167.408

166.279

100.007

Decision Tree

Total Risk

0.408

0.564

0.564

0.564

0.564

0.393

Bias

0.250

0.337

0.337

0.337

0.337

0.225

Variance

0.158

0.227

0.227

0.348

0.227

0.168

Noise

0.000

0.000

0.000

0.121

0.000

0.000

Variance-Bias Ratio

0.631

0.673

0.673

1.033

0.673

0.748

Percent Change from Raw

~

138.303

138.303

138.303

138.303

96.434

Random Forest

Total Risk

0.295

0.396

0.396

0.396

0.396

0.295

Bias

0.286

0.207

0.207

0.207

0.207

0.286

Variance

0.009

0.188

0.188

0.252

0.188

0.009

Noise

0.000

0.000

0.000

0.064

0.000

0.000

Variance-Bias Ratio

0.032

0.909

0.909

1.215

0.909

0.033

Percent Change from Raw

~

134.241

134.241

134.241

134.241

100.002

SVM

Total Risk

0.292

0.290

0.290

0.290

0.290

0.292

Bias

0.287

0.290

0.290

0.290

0.290

0.288

Variance

0.005

0.000

0.000

0.000

0.000

0.005

Noise

0.000

0.000

0.000

0.000

0.000

0.000

Variance-Bias Ratio

0.016

0.000

0.000

0.000

0.000

0.016

Percent Change from Raw

~

99.440

99.440

99.440

99.440

100.218

Gradient Boosting

Total Risk

0.332

0.655

0.655

0.655

0.655

0.332

Bias

0.249

0.540

0.540

0.541

0.540

0.249

Variance

0.082

0.115

0.115

0.132

0.115

0.083

Noise

0.000

0.000

0.000

0.018

0.000

0.000